Machine learning in materials informatics: recent applications and prospects
Top Cited Papers
Open Access
- 13 December 2017
- journal article
- review article
- Published by Springer Science and Business Media LLC in npj Computational Materials
- Vol. 3 (1), 1-13
- https://doi.org/10.1038/s41524-017-0056-5
Abstract
Propelled partly by the Materials Genome Initiative, and partly by the algorithmic developments and the resounding successes of data-driven efforts in other domains, informatics strategies are beginning to take shape within materials science. These approaches lead to surrogate machine learning models that enable rapid predictions based purely on past data rather than by direct experimentation or by computations/simulations in which fundamental equations are explicitly solved. Data-centric informatics methods are becoming useful to determine material properties that are hard to measure or compute using traditional methods—due to the cost, time or effort involved—but for which reliable data either already exists or can be generated for at least a subset of the critical cases. Predictions are typically interpolative, involving fingerprinting a material numerically first, and then following a mapping (established via a learning algorithm) between the fingerprint and the property of interest. Fingerprints, also referred to as “descriptors”, may be of many types and scales, as dictated by the application domain and needs. Predictions may also be extrapolative—extending into new materials spaces—provided prediction uncertainties are properly taken into account. This article attempts to provide an overview of some of the recent successful data-driven “materials informatics” strategies undertaken in the last decade, with particular emphasis on the fingerprint or descriptor choices. The review also identifies some challenges the community is facing and those that should be overcome in the near future.Keywords
This publication has 101 references indexed in Scilit:
- Accelerating materials property predictions using machine learningScientific Reports, 2013
- The Knowledge Gradient for Optimal LearningPublished by Wiley ,2011
- Cluster expansion method for multicomponent systems based on optimal selection of structures for density-functional theory calculationsPhysical Review B, 2009
- Bayesian approach to cluster expansionsPhysical Review B, 2009
- Multi-fidelity optimization via surrogate modellingProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2007
- Efficient cluster expansion for substitutional systemsPhysical Review B, 1992
- Method for relating the structure and properties of chemical compoundsNature, 1974
- An Evaluation of a Substructure Search Screen System Based on Bond-Centered FragmentsJournal of Chemical Documentation, 1974
- Atomic theory for students of metallurgy: William Hume-Rothery, The Institute of Metals, London, 1960, 427 pages, £2 1os, $ 7.50Journal of the Less Common Metals, 1961
- Forces in MoleculesPhysical Review B, 1939